This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Learning Gasoline Direct Injector Dynamics Using Artificial Neural Networks
Technical Paper
2018-01-0863
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
In today’s race for improved fuel economy and lower emissions from gasoline engines, precise metering of delivered fuel is essential. Gasoline Direct Injection fuel systems provide the means for improved combustion efficiency through mixture preparation and better atomization. These improvements can be achieved from both increasing fuel pressure and using multiple injection events, which significantly reduce the required energizing time per injection, and in a number of cases, force the injector to operate at less than full stroke. When the injector operates in this condition, the influence of variation in injector dynamics account for a large percentage of the delivered fuel and require compensation to ensure accurate fuel delivery. Injector dynamics such as opening delay and closing time are influenced by operating conditions such as fuel pressure, energizing time, and temperature. In addition, build variation in injector hardware including spring force, needle lift, and coil resistance have significant influence on the dynamics and continue to vary as the injector ages. Conventional techniques for learning injector dynamics such as injector closing time, require finding an inflection point in the differential voltage signal; however, injectors with weaker signals can compromise the effectiveness of these techniques. This paper’s approach uses machine learning via artificial neural network fitting to analyze Gasoline Direct Injector differential voltage signals to learn injector dynamics over the life of the injector.
The paper uses a standard two-layer feedforward neural network and explores different training algorithms for optimum performance and efficiency. The training sets encompass data under numerous operating conditions along with a wide range of injector hardware variations including parts toward the end of useful life. The predicted injector dynamics from the neural network are compared to the measured data in order to evaluate the performance of the algorithms. Furthermore, multiple injector designs are evaluated in order to assess the robustness of the techniques across platforms.
Recommended Content
Topic
Citation
Lucido, M. and Shibata, J., "Learning Gasoline Direct Injector Dynamics Using Artificial Neural Networks," SAE Technical Paper 2018-01-0863, 2018, https://doi.org/10.4271/2018-01-0863.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 | ||
Unnamed Dataset 3 | ||
Unnamed Dataset 4 | ||
Unnamed Dataset 5 | ||
Unnamed Dataset 6 |
Also In
References
- Piock , W. , Hoffmann , G. , Berndorfer , A. , Salemi , P. et al. Strategies Towards Meeting Future Particulate Matter Emission Requirements in Homogeneous Gasoline Direct Injection Engines SAE Int. J. Engines 4 1 1455 1468 2011 10.4271/2011-01-1212
- Su , J. , Xu , M. , Yin , P. , Gao , Y. et al. Particle Number Emissions Reduction Using Multiple Injection Strategies in a Boosted Spark-Ignition Direct-Injection (SIDI) Gasoline Engine SAE Int. J. Engines 8 1 20 29 2015 10.4271/2014-01-2845
- Chung , J. , Kim , N. , Choi , H. , and Min , K. Study on the Effect of Injection Strategies on Particulate Emission Characteristics under Cold Start Using In-cylinder Visualization SAE Technical Paper 2016-01-0822 2016 10.4271/2016-01-0822
- Whitaker , P. , Kapus , P. , Ogris , M. , and Hollerer , P. Measures to Reduce Particulate Emissions from Gasoline DI engines SAE Int. J. Engines 4 1 1498 1512 2011 10.4271/2011-01-1219
- Lu , H. , Deng , J. , Hu , Z. , Wu , Z. et al. Impact of Control Methods on Dynamic Characteristic of High Speed Solenoid Injectors SAE Int. J. Engines 7 3 1155 1164 2014 10.4271/2014-01-1445
- Kusakabe , R. , Abe , M. , Ehara , H. , Ishikawa , T. et al. Injection Quantity Range Enhancement by Using Current Waveform Control Technique for DI Gasoline Injector SAE Int. J. Engines 7 2 560 567 2014 10.4271/2014-01-1211
- Ito , A. , Kawano , M. , and Fujita , S. ECU Structure Strategy to Detect Lift Timing of GDI Solenoid Injectors with High Precision SAE Technical Paper 2017-01-1628 2017 10.4271/2017-01-1628
- Parotto , M. , Sgatti , S. , and Sensi , F. Advanced GDI Injector Control with Extended Dynamic Range SAE Technical Paper 2013-01-0258 2013 10.4271/2013-01-0258
- Hoffmann , G. , Befrui , B. , Berndorfer , A. , Piock , W. et al. Fuel System Pressure Increase for Enhanced Performance of GDi Multi-Hole Injection Systems SAE Int. J. Engines 7 1 519 527 2014 10.4271/2014-01-1209
- Taglialatela Scafati , F. , Pirozzi , F. , Cannavacciuolo , S. , Allocca , L. et al. Real Time Control of GDI Fuel Injection during Ballistic Operation Mode SAE Technical Paper 2015-24-2428 2015 10.4271/2015-24-2428
- Watanabe , H. , Ichise , S. , Nagaoka , T. , and Tsuchiya , T. Development of Compact and High Performance Fuel Injector using Electromagnetic Field Simulation SAE Technical Paper 2005-32-0019 2005 10.4271/2005-32-0019
- Glasmachers , H. , Melbert , J. , and Koch , A. Sensorless Movement Control of Solenoid Fuel Injectors SAE Technical Paper 2006-01-0407 2006 10.4271/2006-01-0407
- Skiba , S. and Melbert , J. Dosing Performance of Piezo Injectors and Sensorless Closed-Loop Controlled Solenoid Injectors for Gasoline Direct Injection SAE Int. J. Engines 5 2 330 335 2012 10.4271/2012-01-0394
- Steinbrecher , C. , Hamedovic , H. , Rupp , A. , and Wortmann , T. Improved Fuel Metering for Port Fuel Injection by Controlled Valve Operation SAE Int. J. Engines 9 4 2460 2468 2016 10.4271/2016-32-0080
- Tan , T. , Park , J. , and Leteinturier , P. Enhanced Injector Dead Time Compensation by Current Feedback SAE Technical Paper 2016-01-0088 2016 10.4271/2016-01-0088
- Hofmann , O. , Strauß , P. , Schuckert , S. , Huber , B. et al. Identification of Aging Effects in Common Rail Diesel Injectors Using Geometric Classifiers and Neural Networks SAE Technical Paper 2016-01-0813 2016 10.4271/2016-01-0813
- Bertram , A. and Kong , S. Augmentation of an Artificial Neural Network (ANN) Model with Expert Knowledge of Critical Combustion Features for Optimizing a Compression Ignition Engine Using Multiple Injections SAE Technical Paper 2017-01-0701 2017 10.4271/2017-01-0701